Fair bandwidth allocation (FBA) has been studied in optical burst switching (OBS) networks, with the main idea being to map the max‐min fairness in traditional IP networks to the fair‐loss probability in OBS networks. This approach has proven to be fair in terms of the bandwidth allocation for differential connections, but the use of the ErlangB formula to calculate the theoretical loss probability has made this approach applicable only to Poisson flows. Furthermore, it is necessary to have a reasonable fairness measure to evaluate FBA models. This article proposes an approach involving throughput‐based‐FBA, called TFBA, and recommends a new fairness measure that is based on the ratio of the actual throughput to the allocated bandwidth. An analytical model for the performance of the output link with TFBA is also proposed.

Using various offset times to separate differential services is the most common form of service differentiation in optical burst switching networks. In this approach, a larger offset time is given to a higher priority burst, but it causes this burst to have a longer delay. One solution to this problem is to adjust the burst assembly time so that the buffering delay of the higher priority burst is always shorter than that of the lower priority burst. However, this adjustment causes another problem, called delay unfairness, for bursts with differential priorities that share the same path to their destination. This article proposes a new solution for delay fairness using the burst assembly.

Abstract:Burst assembly is an operation at the ingress node of optical burst switching (OBS) networks that aggregates incoming packets from various access networks into larger carriers, called bursts. Depending on the density of incoming packets and the preset time or length thresholds, the completed bursts may have various lengths, but they must be at least equal to a minimum value ( Bmin) to facilitate the switching in existing physical optical switches. If a completed burst is smaller than Bmin , it should be padded by padded bytes and it results in bandwidth utilization inefficiency.One solution to the problem is increasing the assembly time so that completed bursts must be longer than or at least equal to Bmin . However, increasing the assembly time will result in increased end-to-end delay. This article proposes a model of QoS differentiation burst assembly with padding for improving the performance of OBS networks.